In multiple sclerosis (MS), gait impairment is one of the most prominent symptoms. For a sensitive assessment of pathological gait patterns, a comprehensive analysis and processing of several gait analysis systems is necessary. The objective of this work was to determine the best diagnostic gait system (DIERS pedogait, GAITRite system, and Mobility Lab) using six machine learning algorithms for the differentiation between people with multiple sclerosis (pwMS) and healthy controls, between pwMS with and without fatigue and between pwMS with mild and moderate impairment. The data of the three gait systems were assessed on 54 pwMS and 38 healthy controls. Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, and Support Vector Machines (SVM) with linear, radial basis function (rbf) and polynomial kernel were applied for the detection of subtle walking changes. The best performance for a healthy-sick classification was achieved on the DIERS data with a SVM rbf kernel (k = 0.49 ± 0.11). For differentiating between pwMS with mild and moderate disability, the GAITRite data with the SVM linear kernel (k = 0.61 ± 0.06) showed the best performance. This study demonstrates that machine learning methods are suitable for identifying pathologic gait patterns in early MS.
Background The FED method (Fixation, Elongation, Derotation) is a treatment method approach to Patients with scoliosis. The FED method is especially established in Spain and Poland, whereby in Germany it is less well-known. Nevertheless the FED method is within the scope of a research project (Project Number: 19200 BR/3). The purpose of the paper is to characterize the FED method and to highlight the specificities in contrast to the Schroth method, which is international established and especially in Germany. Methods This systematic literature research was conducted in Nov 2017–Jan 2018. Therefore common medical and physiotherapeutic databases were used. Furthermore there was a hand search in selected scientific journals. Only a small number of relevant references were identified. That is why the respective authors were asked to provide the full-texts of their papers and to recommend further references. Results A total of 378 references were identified. After removing duplicates and the content-related selection, 19 references were deemed to be relevant. Based on the analysis of this relevant literature, the FED method was comprehensively characterized. First of all the general structure of the FED method and the scientific evidence for its effectiveness was described. And as a result of the literature research, the operating principles of the FED method were pointed out. Then these operating principles were discussed in comparison with the Schroth method. The Schroth method based on sensomotoric and kinesthetic principles and the correction of the pathologic posture was performed by selective muscle activation and breathing-pattern. Thus, the posture correction will be performed by the patients (auto correction). Compared to the Schroth method, the FED method implements the posture correction by the FED-device. This correction is influenced by mechanical forces with a comparatively high strength and intensity. The repetitive mechanical correction stimulates the sensomotoric system. And due to trophic/biochemical adaptations, the physiological bone growth will be stimulated. Conclusion In total the authors want to clarify, that both treatment methods (Schroth method, FED method) supposed to be applied in consideration of the preconditions of the patients and the pursue of the different treatment goals. Thus, the implementation of treatment methods should be used according to the individual treatment demand and on different stages in the treatment process.
One of the common causes of falls in people with Multiple Sclerosis (pwMS) is walking impairment. Therefore, assessment of gait is of importance in MS. Gait analysis and fall detection can take place in the clinical context using a wide variety of available methods. However, combining these methods while using machine learning algorithms for detecting falls has not been performed. Our objective was to determine the most relevant method for determining fall risk by analyzing eleven different gait data sets with machine learning algorithms. In addition, we examined the most important features of fall detection. A new feature selection ensemble (FS-Ensemble) and four classification models (Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, Support Vector Machine) were used. The FS-Ensemble consisted of four filter methods: Chi-square test, information gain, Minimum Redundancy Maximum Relevance and RelieF. Various thresholds (50%, 25% and 10%) and combination methods (Union, Union 2, Union 3 and Intersection) were examined. Patient-reported outcomes using specialized walking questionnaires such as the 12-item Multiple Sclerosis Walking Scale (MSWS-12) and the Early Mobility Impairment Questionnaire (EMIQ) achieved the best performances with an F1 score of 0.54 for detecting falls. A combination of selected features of MSWS-12 and EMIQ, including the estimation of walking, running and stair climbing ability, the subjective effort as well as necessary concentration and walking fluency during walking, the frequency of stumbling and the indication of avoidance of social activity achieved the best recall of 75%. The Gaussian Naive Bayes was the best classification model for detecting falls with almost all data sets. FS-Ensemble improved the classification models and is an appropriate technique for reducing data sets with a large number of features. Future research on other risk factors, such as fear of falling, could provide further insights.
X-Ray or video raster stereography are used for the progress control of the FED therapy but applied only at intervals of months. A short-term evaluation would allow to adjust the therapy parameters based on the individual therapy progression and could also provide a direct feedback for patient. Therefore, this study aims to isolate parameters for a short-term progression monitoring by applying machine learning algorithms on a set of 130 posture characteristics. A measuring procedure using the DIERS formetric 4D optical measuring system was developed and validated on six patients. The measuring procedure was repeated eight times (four days, each morning and afternoon). Eight parameters were evaluated. The Wilcoxon signed rank test and the Friedman test were used to verify the statistical significance. In order to identify small changes in posture correlating with the applied treatment a hierarchical cluster analysis was performed. The evaluation shows that the parameters pelvic tilt, kyphosis angle and lordosis angle changed significantly between the individual measuring points, but not across all eight parameters. The data is highly dependent on the daily form and cooperation of the patient. The cluster classification is not determined on the basis of the four measurement points, but on the basis of patient individuality. Hierarchical clustering can classify new patients to match them with successful treatment plans of similar cases. By further optimizing the setting parameters a better cluster result should be achieved. More measurements will be made to expand the database. In order to obtain a short-term patient monitoring, other methods of artificial intelligence especially neural networks will be considered.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.